Background
I have created a python module that wraps a c++ program using SWIG. It works just fine, but it has a pretty serious memory leak issue that I think is a result of poorly handled pointers to large map objects. I have very little experience with c++, and I have questions as to whether delete[] can be used on an object created with new in a different function or method.
The program was written in 2007, so excuse the lack of useful c++11 tricks.
The swig extension basically just wraps a single c++ class (Matrix) and a few functions.
Matrix.h
#ifndef __MATRIX__
#define __MATRIX__
#include <string>
#include <vector>
#include <map>
#include <cmath>
#include <fstream>
#include <cstdlib>
#include <stdio.h>
#include <unistd.h>
#include "FileException.h"
#include "ParseException.h"
#define ROUND_TO_INT(n) ((long long)floor(n))
#define MIN(a,b) ((a)<(b)?(a):(b))
#define MAX(a,b) ((a)>(b)?(a):(b))
using namespace std;
class Matrix {
private:
/**
* Split a string following delimiters
*/
void tokenize(const string& str, vector<string>& tokens, const string& delimiters) {
// Skip delimiters at beginning.
string::size_type lastPos = str.find_first_not_of(delimiters, 0);
// Find first "non-delimiter".
string::size_type pos = str.find_first_of(delimiters, lastPos);
while (string::npos != pos || string::npos != lastPos)
{
// Found a token, add it to the vector.
tokens.push_back(str.substr(lastPos, pos - lastPos));
// Skip delimiters. Note the "not_of"
lastPos = str.find_first_not_of(delimiters, pos);
// Find next "non-delimiter"
pos = str.find_first_of(delimiters, lastPos);
}
}
public:
// used for efficiency tests
long long totalMapSize;
long long totalOp;
double ** mat; // the matrix as it is stored in the matrix file
int length;
double granularity; // the real granularity used, greater than 1
long long ** matInt; // the discrete matrix with offset
double errorMax;
long long *offsets; // offset of each column
long long offset; // sum of offsets
long long *minScoreColumn; // min discrete score at each column
long long *maxScoreColumn; // max discrete score at each column
long long *sum;
long long minScore; // min total discrete score (normally 0)
long long maxScore; // max total discrete score
long long scoreRange; // score range = max - min + 1
long long *bestScore;
long long *worstScore;
double background[4];
Matrix() {
granularity = 1.0;
offset = 0;
background[0] = background[1] = background[2] = background[3] = 0.25;
}
Matrix(double pA, double pC, double pG, double pT) {
granularity = 1.0;
offset = 0;
background[0] = pA;
background[1] = pC;
background[2] = pG;
background[3] = pT;
}
~Matrix() {
for (int k = 0; k < 4; k++ ) {
delete[] matInt[k];
}
delete[] matInt;
delete[] mat;
delete[] offsets;
delete[] minScoreColumn;
delete[] maxScoreColumn;
delete[] sum;
delete[] bestScore;
delete[] worstScore;
}
void toLogOddRatio () {
for (int p = 0; p < length; p++) {
double sum = mat[0][p] + mat[1][p] + mat[2][p] + mat[3][p];
for (int k = 0; k < 4; k++) {
mat[k][p] = log((mat[k][p] + 0.25) /(sum + 1)) - log (background[k]);
}
}
}
void toLog2OddRatio () {
for (int p = 0; p < length; p++) {
double sum = mat[0][p] + mat[1][p] + mat[2][p] + mat[3][p];
for (int k = 0; k < 4; k++) {
mat[k][p] = log2((mat[k][p] + 0.25) /(sum + 1)) - log2 (background[k]);
}
}
}
/**
* Transforms the initial matrix into an integer and offseted matrix.
*/
void computesIntegerMatrix (double granularity, bool sortColumns = true);
// computes the complete score distribution between score min and max
void showDistrib (long long min, long long max) {
map<long long, double> *nbocc = calcDistribWithMapMinMax(min,max);
map<long long, double>::iterator iter;
// computes p values and stores them in nbocc[length]
double sum = 0;
map<long long, double>::reverse_iterator riter = nbocc[length-1].rbegin();
while (riter != nbocc[length-1].rend()) {
sum += riter->second;
nbocc[length][riter->first] = sum;
riter++;
}
iter = nbocc[length].begin();
while (iter != nbocc[length].end() && iter->first <= max) {
//cout << (((iter->first)-offset)/granularity) << " " << (iter->second) << " " << nbocc[length-1][iter->first] << endl;
iter ++;
}
}
/**
* Computes the pvalue associated with the threshold score requestedScore.
*/
void lookForPvalue (long long requestedScore, long long min, long long max, double *pmin, double *pmax);
/**
* Computes the score associated with the pvalue requestedPvalue.
*/
long long lookForScore (long long min, long long max, double requestedPvalue, double *rpv, double *rppv);
/**
* Computes the distribution of scores between score min and max as the DP algrithm proceeds
* but instead of using a table we use a map to avoid computations for scores that cannot be reached
*/
map<long long, double> *calcDistribWithMapMinMax (long long min, long long max);
void readMatrix (string matrix) {
vector<string> str;
tokenize(matrix, str, " \t|");
this->length = 0;
this->length = str.size() / 4;
mat = new double*[4];
int idx = 0;
for (int j = 0; j < 4; j++) {
this->mat[j] = new double[this->length];
for (int i = 0; i < this->length; i++) {
mat[j][i] = atof(str.at(idx).data());
idx++;
}
}
str.clear();
}
}; /* Matrix */
#endif
Matrix.cpp
#include "Matrix.h"
#define MEMORYCOUNT
void Matrix::computesIntegerMatrix (double granularity, bool sortColumns) {
double minS = 0, maxS = 0;
double scoreRange;
// computes precision
for (int i = 0; i < length; i++) {
double min = mat[0][i];
double max = min;
for (int k = 1; k < 4; k++ ) {
min = ((min < mat[k][i])?min:(mat[k][i]));
max = ((max > mat[k][i])?max:(mat[k][i]));
}
minS += min;
maxS += max;
}
// score range
scoreRange = maxS - minS + 1;
if (granularity > 1.0) {
this->granularity = granularity / scoreRange;
} else if (granularity < 1.0) {
this->granularity = 1.0 / granularity;
} else {
this->granularity = 1.0;
}
matInt = new long long *[length];
for (int k = 0; k < 4; k++ ) {
matInt[k] = new long long[length];
for (int p = 0 ; p < length; p++) {
matInt[k][p] = ROUND_TO_INT((double)(mat[k][p]*this->granularity));
}
}
this->errorMax = 0.0;
for (int i = 1; i < length; i++) {
double maxE = mat[0][i] * this->granularity - (matInt[0][i]);
for (int k = 1; k < 4; k++) {
maxE = ((maxE < mat[k][i] * this->granularity - matInt[k][i])?(mat[k][i] * this->granularity - (matInt[k][i])):(maxE));
}
this->errorMax += maxE;
}
if (sortColumns) {
// sort the columns : the first column is the one with the greatest value
long long min = 0;
for (int i = 0; i < length; i++) {
for (int k = 0; k < 4; k++) {
min = MIN(min,matInt[k][i]);
}
}
min --;
long long *maxs = new long long [length];
for (int i = 0; i < length; i++) {
maxs[i] = matInt[0][i];
for (int k = 1; k < 4; k++) {
if (maxs[i] < matInt[k][i]) {
maxs[i] = matInt[k][i];
}
}
}
long long **mattemp = new long long *[4];
for (int k = 0; k < 4; k++) {
mattemp[k] = new long long [length];
}
for (int i = 0; i < length; i++) {
long long max = maxs[0];
int p = 0;
for (int j = 1; j < length; j++) {
if (max < maxs[j]) {
max = maxs[j];
p = j;
}
}
maxs[p] = min;
for (int k = 0; k < 4; k++) {
mattemp[k][i] = matInt[k][p];
}
}
for (int k = 0; k < 4; k++) {
for (int i = 0; i < length; i++) {
matInt[k][i] = mattemp[k][i];
}
}
for (int k = 0; k < 4; k++) {
delete[] mattemp[k];
}
delete[] mattemp;
delete[] maxs;
}
// computes offsets
this->offset = 0;
offsets = new long long [length];
for (int i = 0; i < length; i++) {
long long min = matInt[0][i];
for (int k = 1; k < 4; k++ ) {
min = ((min < matInt[k][i])?min:(matInt[k][i]));
}
offsets[i] = -min;
for (int k = 0; k < 4; k++ ) {
matInt[k][i] += offsets[i];
}
this->offset += offsets[i];
}
// look for the minimum score of the matrix for each column
minScoreColumn = new long long [length];
maxScoreColumn = new long long [length];
sum = new long long [length];
minScore = 0;
maxScore = 0;
for (int i = 0; i < length; i++) {
minScoreColumn[i] = matInt[0][i];
maxScoreColumn[i] = matInt[0][i];
sum[i] = 0;
for (int k = 1; k < 4; k++ ) {
sum[i] = sum[i] + matInt[k][i];
if (minScoreColumn[i] > matInt[k][i]) {
minScoreColumn[i] = matInt[k][i];
}
if (maxScoreColumn[i] < matInt[k][i]) {
maxScoreColumn[i] = matInt[k][i];
}
}
minScore = minScore + minScoreColumn[i];
maxScore = maxScore + maxScoreColumn[i];
//cout << "minScoreColumn[" << i << "] = " << minScoreColumn[i] << endl;
//cout << "maxScoreColumn[" << i << "] = " << maxScoreColumn[i] << endl;
}
this->scoreRange = maxScore - minScore + 1;
bestScore = new long long[length];
worstScore = new long long[length];
bestScore[length-1] = maxScore;
worstScore[length-1] = minScore;
for (int i = length - 2; i >= 0; i--) {
bestScore[i] = bestScore[i+1] - maxScoreColumn[i+1];
worstScore[i] = worstScore[i+1] - minScoreColumn[i+1];
}
}
/**
* Computes the pvalue associated with the threshold score requestedScore.
*/
void Matrix::lookForPvalue (long long requestedScore, long long min, long long max, double *pmin, double *pmax) {
map<long long, double> *nbocc = calcDistribWithMapMinMax(min,max);
map<long long, double>::iterator iter;
// computes p values and stores them in nbocc[length]
double sum = nbocc[length][max+1];
long long s = max + 1;
map<long long, double>::reverse_iterator riter = nbocc[length-1].rbegin();
while (riter != nbocc[length-1].rend()) {
sum += riter->second;
if (riter->first >= requestedScore) s = riter->first;
nbocc[length][riter->first] = sum;
riter++;
}
//cout << " s found : " << s << endl;
iter = nbocc[length].find(s);
while (iter != nbocc[length].begin() && iter->first >= s - errorMax) {
iter--;
}
//cout << " s - E found : " << iter->first << endl;
#ifdef MEMORYCOUNT
// for tests, store the number of memory bloc necessary
for (int pos = 0; pos <= length; pos++) {
totalMapSize += nbocc[pos].size();
}
#endif
*pmax = nbocc[length][s];
*pmin = iter->second;
}
/**
* Computes the score associated with the pvalue requestedPvalue.
*/
long long Matrix::lookForScore (long long min, long long max, double requestedPvalue, double *rpv, double *rppv) {
map<long long, double> *nbocc = calcDistribWithMapMinMax(min,max);
map<long long, double>::iterator iter;
// computes p values and stores them in nbocc[length]
double sum = 0.0;
map<long long, double>::reverse_iterator riter = nbocc[length-1].rbegin();
long long alpha = riter->first+1;
long long alpha_E = alpha;
nbocc[length][alpha] = 0.0;
while (riter != nbocc[length-1].rend()) {
sum += riter->second;
nbocc[length][riter->first] = sum;
if (sum >= requestedPvalue) {
break;
}
riter++;
}
if (sum > requestedPvalue) {
alpha_E = riter->first;
riter--;
alpha = riter->first;
} else {
if (riter == nbocc[length-1].rend()) { // path following the remark of the mail
riter--;
alpha = alpha_E = riter->first;
} else {
alpha = riter->first;
riter++;
sum += riter->second;
alpha_E = riter->first;
}
nbocc[length][alpha_E] = sum;
//cout << "Pv(S) " << riter->first << " " << sum << endl;
}
#ifdef MEMORYCOUNT
// for tests, store the number of memory bloc necessary
for (int pos = 0; pos <= length; pos++) {
totalMapSize += nbocc[pos].size();
}
#endif
if (alpha - alpha_E > errorMax) alpha_E = alpha;
*rpv = nbocc[length][alpha];
*rppv = nbocc[length][alpha_E];
delete[] nbocc;
return alpha;
}
// computes the distribution of scores between score min and max as the DP algrithm proceeds
// but instead of using a table we use a map to avoid computations for scores that cannot be reached
map<long long, double> *Matrix::calcDistribWithMapMinMax (long long min, long long max) {
// maps for each step of the computation
// nbocc[length] stores the pvalue
// nbocc[pos] for pos < length stores the qvalue
map<long long, double> *nbocc = new map<long long, double> [length+1];
map<long long, double>::iterator iter;
long long *maxs = new long long[length+1]; // # pos i maximum score reachable with the suffix matrix from i to length-1
maxs[length] = 0;
for (int i = length-1; i >= 0; i--) {
maxs[i] = maxs[i+1] + maxScoreColumn[i];
}
// initializes the map at position 0
for (int k = 0; k < 4; k++) {
if (matInt[k][0]+maxs[1] >= min) {
nbocc[0][matInt[k][0]] += background[k];
}
}
// computes q values for scores greater or equal than min
nbocc[length-1][max+1] = 0.0;
for (int pos = 1; pos < length; pos++) {
iter = nbocc[pos-1].begin();
while (iter != nbocc[pos-1].end()) {
for (int k = 0; k < 4; k++) {
long long sc = iter->first + matInt[k][pos];
if (sc+maxs[pos+1] >= min) {
// the score min can be reached
if (sc > max) {
// the score will be greater than max for all suffixes
nbocc[length-1][max+1] += nbocc[pos-1][iter->first] * background[k]; //pow(4,length-pos-1) ;
totalOp++;
} else {
nbocc[pos][sc] += nbocc[pos-1][iter->first] * background[k];
totalOp++;
}
}
}
iter++;
}
//cerr << " map size for " << pos << " " << nbocc[pos].size() << endl;
}
delete[] maxs;
return nbocc;
}
pytfmpval.i
%module pytfmpval
%{
#include "../src/Matrix.h"
#define SWIG_FILE_WITH_INIT
%}
%include "cpointer.i"
%include "std_string.i"
%include "std_vector.i"
%include "typemaps.i"
%include "../src/Matrix.h"
%pointer_class(double, doublep)
%pointer_class(int, intp)
%nodefaultdtor Matrix;
The c++ functions are called in a python module.
I worry that nbocc in Matrix.cpp is not being properly dereferenced or deleted. Is this use valid?
I have tried using gc.collect() and I am using the multiprocessing module as recommended in this question to call these functions from my python program. I've also tried deleting the Matrix object from within python to no avail.
I'm out of characters, but will provide any additional needed info in the comments as well as I can.
UPDATE: I've removed all of the python code, as it wasn't the issue and made for an absurdly long post. As I stated in the comments below, this was ultimately solved by taking the suggestion of many users and creating a minimal example that exhibited the issue in pure C++. I then used valgrind to identify the problematic pointers created with new and made sure that they were properly dereferenced. This fixed almost all memory leaks. One remains, but it leaks only a few hundred bytes over thousands of iterations and would require refactoring the entire Matrix class, which simply isn't worth the time for what it is. Bad practice, I know. To any other newbie in C++ out there, seriously try to avoid dynamic memory allocation or utilize std::unique_ptr or std::shared_ptr.
Thanks again to everyone who provided input and suggestions.
It’s hard to follow what’s happening, but I’m pretty sure your matrices are not being cleaned up correctly.
In readMatrix, you have a loop over j which contains the line this->mat[j] = new double[this->length];. This allocates memory, which mat[j] points to. This memory needs to be freed at some point, by calling delete[] mat[j] (or some other loop variable). However, in the destructor, you just call delete[] mat, which leaks all of the arrays inside it.
Some general suggestions on cleaning this up:
If you know the bounds of an array, such as that matInt will always have a length of 4, you should declare it with that fixed length (long long* matInt[4] will make an array of four pointers to long long, each of which could be a pointer to an array); this will mean you don’t need to either new or delete it.
If you have a double pointer like double ** mat, and you allocate both the first and second layers of pointers with new[], you need to deallocate the inner layer with delete[] (and you need to do it before you delete[] the outer layer).
If you still have trouble, more of your code will be clear if you remove the methods which don’t seem relevant to the problem. For example, toLogOddRatio doesn’t allocate or deallocate memory at all; it almost certainly isn’t contributing to the problem and you can remove it from the code you post here (once you’ve removed the parts which you think don’t contribute, test again to make sure the problem’s still there; if not then you know that it was one of those parts somehow causing the leak).
Two questions are in play here: managing memory in C++, and then nudging the C++ side from the Python side to clean up. I'm guessing SWIG is generating a wrapper for the Matrix destructor and calling the destructor at some useful time. (I might convince myself of that by having the dtor make some noise.) That should handle the second question.
So let's focus on the C++ side. Passing around a bare map * is a well-known invitation to mischief. Here are two alternatives.
Alternative one: make the map a member of Matrix. Then it gets cleaned up automatically by ~Matrix(). This is the easiest thing. If the lifetime of the map does not exceed the lifetime of the Matrix, then this route will work.
Alternative two: if the map needs to persist after the Matrix object, then instead of passing around map *, use a shared pointer, std::shared_ptr<map>. The shared pointer reference counts the pointee (i.e. the dynamically allocated Matrix). When the ref count goes to zero, it deletes the underlying object.
They both build on the rule to allocate resources (memory in this case) in constructors and deallocate in destructors. This is called RAII (Resource Allocation Is Initialization). Another application of RAII in your code would be to use std::vector<long long> offsets instead of long long *offsets etc. Then you just resize the vectors as needed. When the Matrix is destroyed, the vectors are deleted with no intervention on your part. For the matrix, you could use a vector of vectors, and so on.
to answer your question, yes you can use delete on diffrent function or method. and you should, any memory you allocate in c/c++ you need to free (delete in c++ lingo)
python isn't aware of this memory, it's not a python object, so gc.collect() won't help.
you should add a c function that would take a Matrix struct and free/delete the memory use on that struct. and call it from python, swig in not handling memory allocation (only for the objects swig creates)
I would recommended looking into newer packages other then swig, like cython or cffi (or even NumPy matrix handling, I've heard he's good at)
Related
I'm having successfully embedded a Python script into a C module. The Python script produces a multi-dimensional Numpy array. Whereas the entire calculation in python takes 9 ms, the final tolist() conversion in order to return it to C takes 4 ms alone. I would like to change that by passing the Numpy array as reference and do the iterations in C again. But I can't currently figure out, how this can be done.
There are a lot of samples around, which use the other way around: Passing a Numpy array to a C function which is called from Python, but this is not my use case.
Any pointer welcome.
Ok, it's a while ago but I solved it like so:
My python process delivers an array, containing one array, containing one array, containing N arrays of M floats each. The input is a JPEG image.
Unwrapping it like so:
int predict(PyObject *pyFunction, unsigned char *image_pointer, unsigned long image_len) {
int result = -1;
PyObject *pImage = NULL;
PyObject *pList = NULL;
pImage = PyBytes_FromStringAndSize((const char *)image_pointer, image_len);
if (!pImage) {
fprintf(stderr, "Cannot provide image to python 'predict'\n");
return result;
}
pList = PyObject_CallFunctionObjArgs(pyFunction, pImage, NULL);
Py_DECREF(pImage);
PyArrayObject *pPrediction = reinterpret_cast<PyArrayObject *>(pList);
if (!pPrediction) {
fprintf(stderr, "Cannot predict, for whatever reason\n");
return result;
}
if (PyArray_NDIM(pPrediction) != 4) {
fprintf(stderr, "Prediction failed, returned array with wrong dimensions\n");
} else {
RESULTPTR pResult = reinterpret_cast<RESULTPTR>(PyArray_DATA(pPrediction));
int len0 = PyArray_SHAPE(pPrediction)[0];
int len1 = PyArray_SHAPE(pPrediction)[1];
int len2 = PyArray_SHAPE(pPrediction)[2];
int len3 = PyArray_SHAPE(pPrediction)[3];
for (int i = 0; i < len0; i++) {
int offs1 = i * len1;
for (int j = 0; j < len1; j++) {
int offs2 = j * len2;
for (int k = 0; k < len2; k++) {
int offs3 = k * len3;
for (int l = 0; l < len3; l++) {
float f = (*pResult)[offs1 + offs2 + offs3 + l];
//printf("data: %.8f\n", f);
}
}
}
}
result = 0;
}
Py_XDECREF(pList);
return result;
}
HTH
I am doing benchmarking for finding nearest neighbour for the datapoints. My c++ implementation and python implementation are taking almost same execution time. Shouldn't be c++ works better than the raw python implementation.
C++ Execution Time : 8.506 seconds
Python Execution Time : 8.7202 seconds
C++ Code:
#include <iostream>
#include <random>
#include <map>
#include <cmath>
#include <numeric>
#include <algorithm>
#include <chrono>
#include <vector> // std::iota
using namespace std;
using namespace std::chrono;
double edist(double* arr1, double* arr2, uint n) {
double sum = 0.0;
for (int i=0; i<n; i++) {
sum += pow(arr1[i] - arr2[i], 2);
}
return sqrt(sum); }
template <typename T> vector<size_t> argsort(const vector<T> &v) {
// initialize original index locations
vector<size_t> idx(v.size()); iota(idx.begin(), idx.end(), 0);
// sort indexes based on comparing values in v
sort(idx.begin(), idx.end(),
[&v](size_t i1, size_t i2) {return v[i1] < v[i2];});
return std::vector<size_t>(idx.begin() + 1, idx.end()); }
int main() {
uint N, M;
// cin >> N >> M;
N = 1000;
M = 800;
double **arr = new double*[N];
std::random_device rd; // obtain a random number from hardware
std::mt19937 eng(rd()); // seed the generator
std::uniform_real_distribution<> distr(10.0, 60.0);
for (int i = 0; i < N; i++) {
arr[i] = new double[M];
for(int j=0; j < M; j++) {
arr[i][j] = distr(eng);
}
}
auto start = high_resolution_clock::now();
map<int, vector<size_t> > dist;
for (int i=0; i<N; i++) {
vector<double> distances;
for(int j=0; j<N; j++) {
distances.push_back(edist(arr[i], arr[j], N));
}
dist[i] = argsort(distances);
}
auto stop = high_resolution_clock::now();
auto duration = duration_cast<microseconds>(stop-start);
int dur = duration.count();
cout<<"Time taken by code: "<<dur<<" microseconds"<<endl;
cout<<" In seconds: "<<dur/pow(10,6);
return 0; }
Python Code:
import time
import numpy as np
def comp_inner_raw(i, x):
res = np.zeros(x.shape[0], dtype=np.float64)
for j in range(x.shape[0]):
res[j] = np.sqrt(np.sum((i-x[j])**2))
return res
def nearest_ngbr_raw(x): # x = [[1,2,3],[4,5,6],[7,8,9]]
#print("My array: ",x)
dist = {}
for idx,i in enumerate(x):
#lst = []
lst = comp_inner_raw(i,x)
s = np.argsort(lst)#[1:]
sorted_array = np.array(x)[s][1:]
dist[idx] = s[1:]
return dist
arr = np.random.rand(1000, 800)
start = time.time()
table = nearest_ngbr_raw(arr)
print("Time taken to execute the code using raw python is {}".format(time.time()-start))
Compile Command:
g++ -std=c++11 knn.cpp -o knn
C++ compiler(g++) version for ubuntu 18.04.1: 7.4.0
Coded in c++11
Numpy version : 1.16.2
Edit
Tried with compiler optimization, now it is taking around 1 second.
Can this c++ code be optimized further from coding or any other perspective?
Can this c++ code be optimized further from coding or any other perspective?
I can see at least three optimisations. The first two are easy and should definitely be done but in my testing they end up not impacting the runtime measurably. The third one requires rethinking the code minimally.
edist caculates a costly square root, but you are only using the distance for pairwise comparison. Since the square root function is monotonically increasing, it has no impact on the comparison result. Similarly, pow(x, 2) can be replaced with x * x and this is sometimes faster:
double edist(std::vector<double> const& arr1, std::vector<double> const& arr2, uint n) {
double sum = 0.0;
for (unsigned int i = 0; i < n; i++) {
auto const diff = arr1[i] - arr2[i];
sum += diff * diff;
}
return sum;
}
argsort performs a copy because it returns the indices excluding the first element. If you instead include the first element (change the return statement to return idx;), you avoid a potentially costly copy.
Your matrix is represented as a nested array (and you’re for some reason using raw pointers instead of a nested std::vector). It’s generally more efficient to represent matrices as contiguous N*M arrays: std::vector<double> arr(N * M);. This is also how numpy represents matrices internally. This requires changing the code to calculate the indices.
I'm experiencing a slightly bizarre performance discrepancy between two equatable programs and I cannot reason about the difference for any real reason.
I'm solving Project Euler Problem 46. Both code solutions (one in Python and one in Cpp) get the right answer. However, the python solution seems to be more performant, which is contradictory to what I was expecting.
Do not worry about the actual algorithm being optimal - all I care about is that they are two equatable programs. I'm sure there is a more optimal algorithm.
Python Solution
import math
import time
UPPER_LIMIT = 1000000
HIT_COUNT = 0
def sieveOfErato(number):
sieve = [True] * number
for i in xrange(2, int(math.ceil(math.sqrt(number)))):
if sieve[i]:
for j in xrange(i**2, number, i):
sieve[j] = False
primes = [i for i, val in enumerate(sieve) if i > 1 and val == True]
return set(primes)
def isSquare(number):
ans = math.sqrt(number).is_integer()
return ans
def isAppropriateGolbachNumber(number, possiblePrimes):
global HIT_COUNT
for possiblePrime in possiblePrimes:
if possiblePrime < number:
HIT_COUNT += 1
difference = number - possiblePrime
if isSquare(difference / 2):
return True
return False
if __name__ == '__main__':
start = time.time()
primes = sieveOfErato(UPPER_LIMIT)
answer = -1
for odd in xrange(3, UPPER_LIMIT, 2):
if odd not in primes:
if not isAppropriateGolbachNumber(odd, primes):
answer = odd
break
print('Hit Count: {}'.format(HIT_COUNT))
print('Loop Elapsed Time: {}'.format(time.time() - start))
print('Answer: {}'.format(answer))
C++ Solution
#include <iostream>
#include <unordered_set>
#include <vector>
#include <math.h>
#include <cstdio>
#include <ctime>
int UPPER_LIMIT = 1000000;
std::unordered_set<int> sieveOfErato(int number)
{
std::unordered_set<int> primes;
bool sieve[number+1];
memset(sieve, true, sizeof(sieve));
for(int i = 2; i * i <= number; i++)
{
if (sieve[i] == true)
{
for (int j = i*i; j < number; j+=i)
{
sieve[j] = false;
}
}
}
for(int i = 2; i < number; i++)
{
if (sieve[i] == true)
{
primes.insert(i);
}
}
return primes;
}
bool isPerfectSquare(const int& number)
{
int root(round(sqrt(number)));
return number == root * root;
}
int hitCount = 0;
bool isAppropriateGoldbachNumber(const int& number, const std::unordered_set<int>& primes)
{
int difference;
for (const auto& prime : primes)
{
if (prime < number)
{
hitCount++;
difference = (number - prime)/2;
if (isPerfectSquare(difference))
{
return true;
}
}
}
return false;
}
int main(int argc, char** argv)
{
std::clock_t start;
double duration;
start = std::clock();
std::unordered_set<int> primes = sieveOfErato(UPPER_LIMIT);
int answer = -1;
for(int odd = 3; odd < UPPER_LIMIT; odd+=2)
{
if (primes.find(odd) == primes.end())
{
if (!isAppropriateGoldbachNumber(odd, primes))
{
answer = odd;
break;
}
}
}
duration = (std::clock() - start) / (double) CLOCKS_PER_SEC;
std::cout << "Hit Count: " << hitCount << std::endl;
std::cout << std::fixed << "Loop Elapsed Time: " << duration << std::endl;
std::cout << "Answer: " << answer << std::endl;
}
I'm compiling my cpp code by g++ -std=c++14 file.cpp and then executing with just ./a.out.
On a couple of test runs just using the time command from the command line, I get:
Python
Hit Count: 128854
Loop Elapsed Time: 0.393740177155
Answer: 5777
real 0m0.525s
user 0m0.416s
sys 0m0.049s
C++
Hit Count: 90622
Loop Elapsed Time: 0.993970
Answer: 5777
real 0m1.027s
user 0m0.999s
sys 0m0.013s
Why would there be more hits in the python version and it still be returning more quickly? I would think that more hits, means more iterations, means slower (and it's in python). I'm guessing that there's just a performance blunder in my cpp code, but I haven't found it yet. Any ideas?
I concur with Kunal Puri's answer that a better algorithm and data-structure can improve performance, but it does not answer the core question: Why does the same algorithm, that uses the same data-structure, runs faster with python.
It all boils down to the difference between std::unordered_set and python's set. Note that the same C++ code with std::set runs faster than python's alternative, and if optimization is enabled (with -O2) then C++ code with std::set runs more than 10 times faster than python.
There are several works showing that, and why, std::unordered_set is broken performance-wise. For example you can watch C++Now 2018: You Can Do Better than std::unordered_map: New Improvements to Hash Table Performance. It seems that python does not suffer from these design flaws in its set.
One of the things that make std::unordered_set so poor is the big amount of indirections it mandates to simply reach an element. For example, during iteration, the iterator points to a bucket before the current bucket. Another thing to consider is the poorer cache locality. The set of python seems to prefer to retain the original order of elements, but the GCC's std::unordered_set tends to create a random order. This is the cause of the difference in HIT_COUNT between C++ and python. Once the code starts to use std::set then the HIT_COUNT becomes the same for C++ and python. Retaining the original order during iteration tends to improves the cache locality of nodes in a new process, since they are iterated in the same order as they are allocated (and two adjacent allocations, of a new process, have higher chance to be allocated in consecutive memory addresses).
Apart from compiler optimization as suggested by DYZ, I have some more observations regarding optimization.
1) Use std::vector instead of std::unordered_set.
In your code, you are doing this:
std::unordered_set<int> sieveOfErato(int number)
{
std::unordered_set<int> primes;
bool sieve[number+1];
memset(sieve, true, sizeof(sieve));
for(int i = 2; i * i <= number; i++)
{
if (sieve[i] == true)
{
for (int j = i*i; j < number; j+=i)
{
sieve[j] = false;
}
}
}
for(int i = 2; i < number; i++)
{
if (sieve[i] == true)
{
primes.insert(i);
}
}
return primes;
}
I don't see any reason of using std::unordered_set here. Instead, you could do this:
std::vector<int> sieveOfErato(int number)
{
bool sieve[number+1];
memset(sieve, true, sizeof(sieve));
int numPrimes = 0;
for(int i = 2; i * i <= number; i++)
{
if (sieve[i] == true)
{
for (int j = i*i; j < number; j+=i)
{
sieve[j] = false;
}
numPrimes++;
}
}
std::vector<int> primes(numPrimes);
int j = 0;
for(int i = 2; i < number; i++)
{
if (sieve[i] == true)
{
primes[j++] = i;
}
}
return primes;
}
As far as find() is concerned, you may do this:
int j = 0;
for(int odd = 3; odd < UPPER_LIMIT; odd+=2)
{
while (j < primes.size() && primes[j] < odd) {
j++;
}
if (primes[j] != odd)
{
if (!isAppropriateGoldbachNumber(odd, primes))
{
answer = odd;
break;
}
}
}
2) Pre Compute perfect squares in a std::vector before hand instead of calling sqrt always.
Sorting a list of ints in python 3 seems to be faster than sorting an array of ints in C++. Below is the code for 1 python program and 2 C++ programs that I used for the test. Any reason why the C++ programs are slower? It doesn't make sense to me.
----- Program 1 - python 3.4 -----
from time import time
x = 10000
y = 1000
start = time()
for _ in range(y):
a = list(range(x))
a.reverse()
a.sort()
print(round(time() - start, 2), 'seconds')
----- Program 2 - c++ using sort from algorithm ------
using namespace std;
#include <iostream>
#include <algorithm>
int main(){
int x = 10000;
int y = 1000;
int b[10000];
cout << "start" << endl;
for (int j = 0; j < y; j++){
for (int i = 0; i < x; i++){
b[i] = x - i;
} // still slower than python with this clause taken out
sort(b, b + x); // regular sort
}
cout << "done";
system("pause");
}
----- Program 3 - c++ using hand written merge sort ------
using namespace std;
#include <iostream>
void merge(int * arr, int *temp, int first_start, int second_start, int second_finish){
int a1 = first_start, b1 = second_start, r = 0;
while (a1 < second_start && b1 < second_finish){
if (arr[a1] < arr[b1]){
temp[r] = arr[a1];
a1++; r++;
}
else {
temp[r] = arr[b1];
b1++; r++;
}
}
if (a1 < second_start){
while (a1 < second_start){
temp[r] = arr[a1];
a1++; r++;
}
}
else {
while (b1 < second_finish){
temp[r] = arr[b1];
b1++; r++;
}
}
for (int i = first_start; i < second_finish; i++){
arr[i] = temp[i - first_start];
}
}
void merge_sort(int *a, int a_len, int *temp){
int c = 1, start = 0;
while (c < a_len){
while (start + c * 2 < a_len){
merge(a, temp, start, start + c, start + c * 2);
start += c * 2;
}
if (start + c <= a_len){
merge(a, temp, start, start + c, a_len);
}
c *= 2; start = 0;
}
}
int main(){
int x = 10000; // size of array to be sorted
int y = 1000; // number of times to sort it
int b[10000], temp[10000];
cout << "start" << endl;
for (int j = 0; j < y; j++){
for (int i = 0; i < x; i++){
b[i] = x - i; // reverse sorted array (even with this assignment taken out still runs slower than python)
}
merge_sort(b, x, temp);
}
cout << "done";
system("pause");
}
The core reason is no doubt timsort -- http://en.wikipedia.org/wiki/Timsort -- first conceived by Tim Peters for Python though now also in some Java VMs (for non-primitives only).
It's a truly amazing algorithm and you can find a C++ implementation at https://github.com/swenson/sort for example.
Lesson to retain: the proper architecture and algorithms can let you run circles around supposedly-faster languages if the latter are using less-perfect A & As!-) So, if you have really big problems to solve, deal with determining perfect architecture and algorithms first -- the language and optimizations within it are inevitably lower-priority issues.
I wrote same program in C++ and Python. In Python it takes unusual amount of time(Actually I did't get answer in it). Can anybody explain why is that?
C++ code:
#include<iostream>
using namespace std;
int main(){
int n = 1000000;
int *solutions = new int[n];
for (int i = 1; i <= n; i++){
solutions[i] = 0;
}
for (int v = 1; v <= n; v++){
for (int u = 1; u*v <= n; u++){
if ((3 * v>u) & (((u + v) % 4) == 0) & (((3 * v - u) % 4) == 0)){
solutions[u*v]++;
}
}
}
int count = 0;
for (int i = 1; i < n; i++){
if ((solutions[i])==10)
count += 1;
}
cout << count;
}
Python code:
n=1000000
l=[0 for x in range(n+1)]
for u in range(1,n+1):
v=1
while u*v<n+1:
if (((u+v)%4)==0) and (((3*v-u)%4)==0) and (3*v>u):
l[u*v]+=1
v+=1
l.count(10)
You can try optimizing this loop, for example make it a single block with no ifs in it, or otherwise use a module in C.
C++ compiler does optimalizations Python runtime can't, so with pure interpreter you will never get performance being anything close.
And 1M interactions is a lot, I woulnt start with any interpreter in that range, you'd be better doing it in a browser and JavaScript.